Welcome to RCAC Documentation¶
New to RCAC?¶
Follow these steps to get up and running on RCAC clusters.
-
Get an Account
Request access to RCAC computing resources through your Purdue career account or an ACCESS account.
-
Connect to a RCAC Cluster
Learn how to log in via SSH, set up your environment, and access the cluster for the first time.
-
Transfer Your Data
Move files to and from the cluster using SCP, SFTP, Globus, or the research data depot.
-
Submit Your First Job
Write a Slurm batch script, submit it to the scheduler, and monitor your job's progress.
-
Install Software
Find pre-installed modules via the LMOD system or request software from the RCAC help desk.
HPC User Guides¶
-
Anvil
NSF-funded capacity cluster for the national research community. Features AMD EPYC Milan CPUs, NVIDIA A100 GPUs, and large-memory nodes. Available through ACCESS allocations.
128 cores/node | 256GB-1TB RAM | A100/H100 GPUs
-
Gautschi
Purdue's community cluster for faculty and research groups. Powered by AMD EPYC Genoa CPUs and NVIDIA H100 GPUs. Access through the community cluster purchase program.
192 cores/node | 384GB-1.5TB RAM | H100 GPUs
-
Bell
Community Cluster optimized for communities running traditional, tightly-coupled science and engineering applications. Built through a partnership with Dell and AMD, Bell consists of compute nodes with two 64-core AMD EPYC "Rome" processors and 256 GB of memory.
128 cores/node | 256 GB RAM | 100 Gbps HDR Infiniband
-
Negishi
Community Cluster optimized for communities running traditional, tightly-coupled science and engineering applications. Built through a partnership with Dell and AMD, Negishi consists of compute nodes with two 64-core AMD EPYC "Milan" processors and 256 GB of memory.
128 cores/node | 256 GB RAM | 100 Gbps HDR Infiniband
-
Gilbreth
Community Cluster optimized for communities running GPU intensive applications such as machine learning. Consists of Dell compute nodes with Intel Xeon processors and Nvidia Tesla GPUs.
-
Scholar
A small cluster suitable for classroom learning about high performance computing. Consists of 6 interactive login servers and 16 batch worker nodes, accessible as a typical cluster with a job scheduler or as an interactive resource with a desktop-like environment.
RCAC Resources¶
-
RCAC Blogs
Dive into insights from RCAC staff covering best practices, new features, and tips for getting the most out of our computing resources.
-
Workshops & Tutorials
Hands-on training materials from RCAC workshops, covering topics from introductory Linux to advanced parallel computing and GPU programming.
-
Software Catalog
Browse the complete catalog of software installed across RCAC clusters, including versions, module names, and usage instructions.
-
Datasets
Access curated research datasets hosted on RCAC systems, including genomics references, machine learning benchmarks, and domain-specific collections.
Need Help?¶
-
Email Support
Reach the RCAC help desk for account issues, software requests, and technical questions.
-
Community Discord
A community Discord for Purdue researchers, RCAC staff, and other organizations to discuss research computing in real time.
-
GitHub
Report documentation issues, suggest improvements, or contribute to RCAC open-source projects.
-
Contact Details
Find office hours, phone numbers, and other ways to connect with the RCAC support team.